Commit
•
f3e593b
1
Parent(s):
99c61d4
Initial commit
Browse files- config.json +24 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4096,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"transformers_version": "4.5.1",
|
21 |
+
"type_vocab_size": 2,
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ba930f9c9716b833439e0434f52d8dee618a79f516c9f585ce7f5cb0a25d055
|
3 |
+
size 2681398353
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:132fae0da657658ca11d9e2d212955772230b172d08c7662ca4538f332b64ed3
|
3 |
+
size 1340746825
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1acca92a8b10bd06cc866eafb8aeb9d4f85bcdb2d57143bebcfe2bc573e5d33a
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-uncased"}
|
trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6158979909555603,
|
3 |
+
"best_model_checkpoint": "test-glue/checkpoint-1070",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 1605,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.93,
|
12 |
+
"learning_rate": 1.3769470404984425e-05,
|
13 |
+
"loss": 0.438,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 0.44685283303260803,
|
19 |
+
"eval_matthews_correlation": 0.5729657494988228,
|
20 |
+
"eval_runtime": 4.6654,
|
21 |
+
"eval_samples_per_second": 223.559,
|
22 |
+
"step": 535
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 1.87,
|
26 |
+
"learning_rate": 7.538940809968847e-06,
|
27 |
+
"loss": 0.248,
|
28 |
+
"step": 1000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 0.4980889558792114,
|
33 |
+
"eval_matthews_correlation": 0.6158979909555603,
|
34 |
+
"eval_runtime": 4.6816,
|
35 |
+
"eval_samples_per_second": 222.789,
|
36 |
+
"step": 1070
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.8,
|
40 |
+
"learning_rate": 1.308411214953271e-06,
|
41 |
+
"loss": 0.147,
|
42 |
+
"step": 1500
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"eval_loss": 0.6851685643196106,
|
47 |
+
"eval_matthews_correlation": 0.6142064528308289,
|
48 |
+
"eval_runtime": 4.6892,
|
49 |
+
"eval_samples_per_second": 222.426,
|
50 |
+
"step": 1605
|
51 |
+
}
|
52 |
+
],
|
53 |
+
"max_steps": 1605,
|
54 |
+
"num_train_epochs": 3,
|
55 |
+
"total_flos": 1071782270269488.0,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": null
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6068b4bdc4221f296f828ec39d9b73ab569e35c7954ee7beb9242797ea2e4195
|
3 |
+
size 2351
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|